From: Genjian Zhang zhanggenjian@kylinos.cn

This reverts commit 13b2856037a651ba3ab4a8b25ecab3e791926da3.

This patch lost a unlock loop_ctl_mutex in loop_get_status(...), which caused syzbot to report a UAF issue.The upstream patch does not have this issue. Therefore, we revert this patch and directly apply the upstream patch later on.

Risk use-after-free as reported by syzbot：

[ 84.669496] ================================================================== [ 84.670021] BUG: KASAN: use-after-free in __mutex_lock.isra.9+0xc13/0xcb0 [ 84.670433] Read of size 4 at addr ffff88808dba43b8 by task syz-executor.22/14230 [ 84.670885] [ 84.670987] CPU: 1 PID: 14230 Comm: syz-executor.22 Not tainted 5.4.270 #4 [ 84.671397] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1kylin1 04/01/2014 [ 84.671927] Call Trace: [ 84.672085] dump_stack+0x94/0xc7 [ 84.672293] ? __mutex_lock.isra.9+0xc13/0xcb0 [ 84.672569] print_address_description.constprop.6+0x16/0x220 [ 84.672915] ? __mutex_lock.isra.9+0xc13/0xcb0 [ 84.673187] ? __mutex_lock.isra.9+0xc13/0xcb0 [ 84.673462] __kasan_report.cold.9+0x1a/0x32 [ 84.673723] ? __mutex_lock.isra.9+0xc13/0xcb0 [ 84.673993] kasan_report+0x10/0x20 [ 84.674208] __mutex_lock.isra.9+0xc13/0xcb0 [ 84.674468] ? __mutex_lock.isra.9+0x617/0xcb0 [ 84.674739] ? ww_mutex_lock_interruptible+0x100/0x100 [ 84.675055] ? ww_mutex_lock_interruptible+0x100/0x100 [ 84.675369] ? kobject_get_unless_zero+0x144/0x190 [ 84.675668] ? kobject_del+0x60/0x60 [ 84.675893] ? __module_get+0x120/0x120 [ 84.676128] ? __mutex_lock_slowpath+0x10/0x10 [ 84.676399] mutex_lock_killable+0xde/0xf0 [ 84.676652] ? __mutex_lock_killable_slowpath+0x10/0x10 [ 84.676967] ? __mutex_lock_slowpath+0x10/0x10 [ 84.677243] ? disk_block_events+0x1d/0x120 [ 84.677509] lo_open+0x16/0xc0 [ 84.677701] ? lo_compat_ioctl+0x160/0x160 [ 84.677954] __blkdev_get+0xb0f/0x1160 [ 84.678185] ? bd_may_claim+0xd0/0xd0 [ 84.678410] ? bdev_disk_changed+0x190/0x190 [ 84.678674] ? _raw_spin_lock+0x7c/0xd0 [ 84.678915] ? _raw_write_lock_bh+0xd0/0xd0 [ 84.679172] blkdev_get+0x9b/0x290 [ 84.679381] ? ihold+0x1a/0x40 [ 84.679574] blkdev_open+0x1bd/0x240 [ 84.679794] do_dentry_open+0x439/0x1000 [ 84.680035] ? blkdev_get_by_dev+0x60/0x60 [ 84.680286] ? __x64_sys_fchdir+0x1a0/0x1a0 [ 84.680557] ? inode_permission+0x86/0x320 [ 84.680814] path_openat+0x998/0x4120 [ 84.681044] ? stack_trace_consume_entry+0x160/0x160 [ 84.681348] ? do_futex+0x136/0x1880 [ 84.681568] ? path_mountpoint+0xb50/0xb50 [ 84.681823] ? save_stack+0x4d/0x80 [ 84.682038] ? save_stack+0x19/0x80 [ 84.682253] ? __kasan_kmalloc.constprop.6+0xc1/0xd0 [ 84.682553] ? kmem_cache_alloc+0xc7/0x210 [ 84.682804] ? getname_flags+0xc4/0x560 [ 84.683045] ? do_sys_open+0x1ce/0x450 [ 84.683272] ? do_syscall_64+0x9a/0x330 [ 84.683509] ? entry_SYSCALL_64_after_hwframe+0x5c/0xc1 [ 84.683826] ? _raw_spin_lock+0x7c/0xd0 [ 84.684063] ? _raw_write_lock_bh+0xd0/0xd0 [ 84.684319] ? futex_exit_release+0x60/0x60 [ 84.684574] ? kasan_unpoison_shadow+0x30/0x40 [ 84.684844] ? __kasan_kmalloc.constprop.6+0xc1/0xd0 [ 84.685149] ? get_partial_node.isra.83.part.84+0x1e5/0x340 [ 84.685485] ? __fget_light+0x1d1/0x550 [ 84.685721] do_filp_open+0x197/0x270 [ 84.685946] ? may_open_dev+0xd0/0xd0 [ 84.686172] ? kasan_unpoison_shadow+0x30/0x40 [ 84.686443] ? __kasan_kmalloc.constprop.6+0xc1/0xd0 [ 84.686743] ? __alloc_fd+0x1a3/0x580 [ 84.686973] do_sys_open+0x2c7/0x450 [ 84.687195] ? filp_open+0x60/0x60 [ 84.687406] ? __x64_sys_timer_settime32+0x280/0x280 [ 84.687707] do_syscall_64+0x9a/0x330 [ 84.687931] ? syscall_return_slowpath+0x17a/0x230 [ 84.688221] entry_SYSCALL_64_after_hwframe+0x5c/0xc1 [ 84.688524] [ 84.688622] Allocated by task 14056: [ 84.688842] save_stack+0x19/0x80 [ 84.689044] __kasan_kmalloc.constprop.6+0xc1/0xd0 [ 84.689333] kmem_cache_alloc_node+0xe2/0x230 [ 84.689600] copy_process+0x165c/0x72d0 [ 84.689833] _do_fork+0xf9/0x9a0 [ 84.690032] __x64_sys_clone+0x17a/0x200 [ 84.690271] do_syscall_64+0x9a/0x330 [ 84.690496] entry_SYSCALL_64_after_hwframe+0x5c/0xc1 [ 84.690800] [ 84.690903] Freed by task 0: [ 84.691081] save_stack+0x19/0x80 [ 84.691287] __kasan_slab_free+0x125/0x170 [ 84.691535] kmem_cache_free+0x7a/0x2a0 [ 84.691774] __put_task_struct+0x1ec/0x4a0 [ 84.692023] delayed_put_task_struct+0x178/0x1d0 [ 84.692303] rcu_core+0x538/0x16c0 [ 84.692512] __do_softirq+0x175/0x63d [ 84.692741] [ 84.692840] The buggy address belongs to the object at ffff88808dba4380 [ 84.692840] which belongs to the cache task_struct of size 3328 [ 84.693584] The buggy address is located 56 bytes inside of [ 84.693584] 3328-byte region [ffff88808dba4380, ffff88808dba5080) [ 84.694272] The buggy address belongs to the page: [ 84.694563] page:ffffea000236e800 refcount:1 mapcount:0 mapping:ffff8881838acdc0 index:0x0 compound_mapcount: 0 [ 84.695166] flags: 0x100000000010200(slab|head) [ 84.695457] raw: 0100000000010200 dead000000000100 dead000000000122 ffff8881838acdc0 [ 84.695919] raw: 0000000000000000 0000000000090009 00000001ffffffff 0000000000000000 [ 84.696375] page dumped because: kasan: bad access detected [ 84.696705] [ 84.696801] Memory state around the buggy address: [ 84.697089] ffff88808dba4280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 84.697519] ffff88808dba4300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 84.697945] >ffff88808dba4380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 84.698371] ^ [ 84.698674] ffff88808dba4400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 84.699111] ffff88808dba4480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 84.699537] ================================================================== [ 84.699965] Disabling lock debugging due to kernel taint

Reported-by: k2ci kernel-bot@kylinos.cn Signed-off-by: Genjian Zhang zhanggenjian@kylinos.cn --- drivers/block/loop.c | 5 ----- 1 file changed, 5 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d8821c9cb170..fced67ab1068 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1397,11 +1397,6 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) info->lo_number = lo->lo_number; info->lo_offset = lo->lo_offset; info->lo_sizelimit = lo->lo_sizelimit; - - /* loff_t vars have been assigned __u64 */ - if (lo->lo_offset < 0 || lo->lo_sizelimit < 0) - return -EOVERFLOW; - info->lo_flags = lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);

From: Martijn Coenen maco@android.com

[ Upstream commit 083a6a50783ef54256eec3499e6575237e0e3d53 ]

sector_t is now always u64, so we don't need to check for truncation.

Signed-off-by: Martijn Coenen maco@android.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Genjian Zhang zhanggenjian@kylinos.cn --- drivers/block/loop.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c index eb7b9629f6dd..45237d44a867 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -226,24 +226,20 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) blk_mq_unfreeze_queue(lo->lo_queue); }

-static int +static void figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { loff_t size = get_size(offset, sizelimit, lo->lo_backing_file); - sector_t x = (sector_t)size; struct block_device *bdev = lo->lo_device;

- if (unlikely((loff_t)x != size)) - return -EFBIG; if (lo->lo_offset != offset) lo->lo_offset = offset; if (lo->lo_sizelimit != sizelimit) lo->lo_sizelimit = sizelimit; - set_capacity(lo->lo_disk, x); + set_capacity(lo->lo_disk, size); bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9); /* let user-space know about the new size */ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); - return 0; }

static inline int @@ -1002,10 +998,8 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, !file->f_op->write_iter) lo_flags |= LO_FLAGS_READ_ONLY;

- error = -EFBIG; size = get_loop_size(lo, file); - if ((loff_t)(sector_t)size != size) - goto out_unlock; + error = loop_prepare_queue(lo); if (error) goto out_unlock; @@ -1326,10 +1320,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) lo->lo_device->bd_inode->i_mapping->nrpages); goto out_unfreeze; } - if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { - err = -EFBIG; - goto out_unfreeze; - } + figure_loop_size(lo, info->lo_offset, info->lo_sizelimit); }

memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); @@ -1532,7 +1523,9 @@ static int loop_set_capacity(struct loop_device *lo) if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO;

- return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); + figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); + + return 0; }

static int loop_set_dio(struct loop_device *lo, unsigned long arg)

From: Martijn Coenen maco@android.com

[ Upstream commit b0bd158dd630bd47640e0e418c062cda1e0da5ad ]

figure_loop_size() calculates the loop size based on the passed in parameters, but at the same time it updates the offset and sizelimit parameters in the loop device configuration. That is a somewhat unexpected side effect of a function with this name, and it is only only needed by one of the two callers of this function - loop_set_status().

Move the lo_offset and lo_sizelimit assignment back into loop_set_status(), and use the newly factored out functions to validate and apply the newly calculated size. This allows us to get rid of figure_loop_size() in a follow-up commit.

Signed-off-by: Martijn Coenen maco@android.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Genjian Zhang zhanggenjian@kylinos.cn --- drivers/block/loop.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 78bfba4bce8a..54f0f592423d 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -249,11 +249,6 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);

- if (lo->lo_offset != offset) - lo->lo_offset = offset; - if (lo->lo_sizelimit != sizelimit) - lo->lo_sizelimit = sizelimit; - loop_set_size(lo, size); }

@@ -1271,6 +1266,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) kuid_t uid = current_uid(); struct block_device *bdev; bool partscan = false; + bool size_changed = false;

err = mutex_lock_killable(&loop_ctl_mutex); if (err) @@ -1292,6 +1288,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)

if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { + size_changed = true; sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); } @@ -1299,6 +1296,15 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue);

+ if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) { + /* If any pages were dirtied after invalidate_bdev(), try again */ + err = -EAGAIN; + pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + __func__, lo->lo_number, lo->lo_file_name, + lo->lo_device->bd_inode->i_mapping->nrpages); + goto out_unfreeze; + } + err = loop_release_xfer(lo); if (err) goto out_unfreeze; @@ -1322,19 +1328,8 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (err) goto out_unfreeze;

- if (lo->lo_offset != info->lo_offset || - lo->lo_sizelimit != info->lo_sizelimit) { - /* kill_bdev should have truncated all the pages */ - if (lo->lo_device->bd_inode->i_mapping->nrpages) { - err = -EAGAIN; - pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", - __func__, lo->lo_number, lo->lo_file_name, - lo->lo_device->bd_inode->i_mapping->nrpages); - goto out_unfreeze; - } - figure_loop_size(lo, info->lo_offset, info->lo_sizelimit); - } - + lo->lo_offset = info->lo_offset; + lo->lo_sizelimit = info->lo_sizelimit; memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; @@ -1358,6 +1353,12 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) lo->lo_key_owner = uid; }

+ if (size_changed) { + loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, + lo->lo_backing_file); + loop_set_size(lo, new_size); + } + loop_config_discard(lo);

/* update dio if lo_offset or transfer is changed */

From: Siddh Raman Pant code@siddh.me

[ Upstream commit c490a0b5a4f36da3918181a8acdc6991d967c5f3 ]

The userspace can configure a loop using an ioctl call, wherein a configuration of type loop_config is passed (see lo_ioctl()'s case on line 1550 of drivers/block/loop.c). This proceeds to call loop_configure() which in turn calls loop_set_status_from_info() (see line 1050 of loop.c), passing &config->info which is of type loop_info64*. This function then sets the appropriate values, like the offset.

loop_device has lo_offset of type loff_t (see line 52 of loop.c), which is typdef-chained to long long, whereas loop_info64 has lo_offset of type __u64 (see line 56 of include/uapi/linux/loop.h).

The function directly copies offset from info to the device as follows (See line 980 of loop.c): lo->lo_offset = info->lo_offset;

This results in an overflow, which triggers a warning in iomap_iter() due to a call to iomap_iter_done() which has: WARN_ON_ONCE(iter->iomap.offset > iter->pos);

Thus, check for negative value during loop_set_status_from_info().

Bug report: https://syzkaller.appspot.com/bug?id=c620fe14aac810396d3c3edc9ad73848bf69a29...

Reported-and-tested-by: syzbot+a8e049cd3abd342936b6@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Siddh Raman Pant code@siddh.me Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20220823160810.181275-1-code@siddh.me Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Genjian Zhang zhanggenjian@kylinos.cn --- drivers/block/loop.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c index eadb189be0cc..c999eef4e345 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1298,6 +1298,11 @@ loop_set_status_from_info(struct loop_device *lo,

lo->lo_offset = info->lo_offset; lo->lo_sizelimit = info->lo_sizelimit; + + /* loff_t vars have been assigned __u64 */ + if (lo->lo_offset < 0 || lo->lo_sizelimit < 0) + return -EOVERFLOW; + memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0;